claude-cli

Automates Claude Code CLI invocations for headless sessions and JSON output.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Git-Fg/taches-principled-light --skill claude-cli-git-fg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-cli
Source: https://github.com/Git-Fg/taches-principled-light/tree/main/skills/claude-cli
Command: npx skills add https://github.com/Git-Fg/taches-principled-light --skill claude-cli-git-fg

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

The claude-cli Skill streamlines automation and programmability of Claude Code, allowing users to initiate headless sessions, manage models and permissions, and execute code reviews programmatically.

Core Features & Use Cases

  • Headless Sessions: Run Claude Code in a non-interactive mode for background tasks and automated workflows.
  • JSON Output: Get structured JSON responses from Claude Code for further processing.
  • Model and Permission Control: Dynamically adjust the model and permission modes for different invocations.
  • Cloud Code Reviews: Execute cloud-hosted code reviews programmatically.
  • Use Case: For developers needing to integrate Claude Code into their build pipelines or automated testing environments, this Skill provides the necessary tools to drive Claude Code programmatically.

Quick Start

Use the claude-cli skill to run a headless Claude session to generate a code review for the current branch.

Frequently Asked Questions about claude-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Claude Code in a headless session for automated workflows?

The claude-cli Skill automates Claude Code CLI invocations to run headless sessions in non-interactive mode for background tasks. It enables programmatic execution of automated workflows without manual intervention.

How do I get JSON output from Claude Code for script processing?

The claude-cli Skill drives Claude Code programmatically to return structured JSON output. This format allows scripts to capture and parse responses directly for further automated processing.

Can I dynamically adjust model and permission modes for Claude Code CLI invocations?

Yes, the claude-cli Skill supports per-invocation flags to dynamically adjust model and permission modes for Claude Code CLI. This allows granular control over automated tasks and cloud code reviews.

Does the claude-cli Skill require Claude Code CLI to be installed locally?

Yes, using the claude-cli Skill requires the Claude Code CLI to be installed and accessible in your environment. It acts as a programmatic wrapper to drive the existing CLI for automation.

What is the best way to integrate Claude Code into a build pipeline for code reviews?

The claude-cli Skill integrates Claude Code into build pipelines by programmatically executing cloud-hosted code reviews. It returns structured JSON results, enabling seamless automated code analysis within CI/CD environments.